Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a frozen or EMA version of themselves that receives privileged information. Its application to multimodal large language models (MLLMs), however, remains largely unexplored. Recent approaches use privileged visual information, such as image crops…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
